A remote real-time monitoring method for port shore power systems

Abstract

The present application provides a remote real-time monitoring method for a port shore power system, which relates to the technical field of power system monitoring. The method extracts power generation parameters from a mutual induction data set during power transmission of the shore power system; performs an anomaly test on the mutual induction data set to obtain a mutual induction error, and determines an error sensing node based on the mutual induction error and the power generation parameters; determines the abnormal probability of power transmission of the shore power system through the topological structure of the transmission node and the error sensing node, and then performs a split point anomaly analysis on the abnormal probability to obtain an abnormal isolation path; predicts faults of the error sensing node based on historical power transmission data to obtain an abnormal node sequence, and then determines an abnormal load factor through the abnormal node sequence and the abnormal isolation path; and performs abnormal monitoring of the port shore power system based on the abnormal load factor to obtain a monitoring result of the abnormal transmission node. The present application can realize real-time fault monitoring and isolation of the port shore power system, thereby improving the credibility of the shore power system monitoring results.

Description

Technical Field

[0001] The present application relates to the technical field of power system monitoring, and more specifically, to a remote real-time monitoring method for a port shore power system. Background Art

[0002] With the continuous development of smart grids and energy informatization, the monitoring and fault detection technology of power systems has gradually evolved from traditional manual inspections and static alarms to a real-time monitoring system that relies on sensor networks, edge computing, and data intelligent analysis. Through the continuous collection and analysis of system operation data, it can achieve dynamic perception of the grid operation status, fault warning and rapid response, thereby improving the stability and safety of grid operation.

[0003] Port shore power systems offer significant economic and environmental benefits by providing shore power to ships docked at ports, reducing fuel consumption and environmental pollution. However, due to the complex power transmission structure, frequent connection / disconnection, and various external interference factors involved in their operation, fault location and anomaly analysis in shore power systems present significant challenges. Existing methods, such as setting fixed thresholds to trigger alarms, recording transmission node status, and performing static trend analysis, can be used to monitor port shore power systems. However, these technologies lack dynamic correlation analysis mechanisms, making it impossible to establish electrical logic and error propagation paths between multiple data transmission nodes. Furthermore, these technologies can only respond passively after a fault occurs, failing to predict it in a timely manner. This makes it difficult to accurately identify the transmission node at the source of the fault, resulting in poor robustness in dealing with complex fault modes and low reliability of monitoring results. Therefore, achieving real-time fault monitoring and isolation in port shore power systems to improve the reliability of shore power system monitoring results has become a challenge facing the industry. Summary of the Invention

[0004] The present application provides a remote real-time monitoring method for a port shore power system, which can realize real-time fault monitoring and isolation of the port shore power system, thereby improving the credibility of the shore power system monitoring results.

[0005] The present application provides a remote real-time monitoring method for a port shore power system, the real-time monitoring method comprising the following steps:

[0006] collecting a mutual induction data set during power transmission of the port shore power system, and extracting power generation parameters from the mutual induction data set;

[0007] performing an anomaly test on the mutual induction data set to obtain a mutual induction error, and determining an error sensing node based on the mutual induction error and the power generation parameter;

[0008] Determining the abnormal probability of shore power system power transmission through the topological structure of the port shore power system transmission node and the error sensing node, and then performing splitting point abnormality analysis on the abnormal probability to obtain an abnormal isolation path;

[0009] Acquire historical power transmission data of the port shore power system, perform fault prediction on the error sensing node based on the historical power transmission data, obtain an abnormal node sequence, and then determine an abnormal load factor based on the abnormal node sequence and the abnormal isolation path;

[0010] Based on the abnormal load factor, the port shore power system is monitored for abnormalities to obtain monitoring results of abnormal transmission nodes.

[0011] In this embodiment, a mutual inductance data set of the port shore power system is collected through a preset sensor array.

[0012] In this embodiment, the power generation parameters are extracted from the mutual induction data set by a data extraction model.

[0013] In this embodiment, performing an abnormality check on the mutual inductance data set to obtain the mutual inductance error specifically includes:

[0014] performing denoising, normalization, and synchronization correction processing on the mutual induction data in the mutual induction data set to obtain processed mutual induction data;

[0015] The processed mutual inductance data is subjected to time series anomaly detection and analysis to obtain the mutual inductance error.

[0016] In this embodiment, determining the error sensing node based on the mutual inductance error and the power generation parameter specifically includes:

[0017] Mapping the mutual inductance error and the power generation parameter to the same scale through normalization processing to obtain normalized mutual inductance error and power generation parameter;

[0018] The abnormal sensitivity of the transmission node of the port shore power system is determined based on the normalized mutual inductance error and power generation parameters;

[0019] The abnormality detection nodes of the port shore power system are screened according to the abnormality sensitivity to obtain error sensing nodes.

[0020] In this embodiment, determining the abnormal probability of power transmission of the shore power system by using the topological structure of the port shore power system transmission node and the error sensing node specifically includes:

[0021] Convert the topological structure of the port shore power system transmission nodes into a directed weighted graph;

[0022] Performing error propagation deduction on the directed weighted graph according to the error sensing node to obtain abnormal transmission probabilities of different transmission nodes in the directed weighted graph;

[0023] The abnormal probability of shore power system power transmission is determined by all abnormal transmission probabilities.

[0024] In this embodiment, performing split point anomaly analysis on the anomaly probability to obtain an anomaly isolation path specifically includes:

[0025] dividing abnormal splitting points according to the abnormal probability of power transmission of the shore power system;

[0026] Performing isolation processing on the abnormal splitting points to obtain an abnormal transmission node subgraph of the topological structure of the port shore power system transmission nodes;

[0027] The abnormal isolation path is determined through the abnormal transmission node subgraph of the topological structure of the port shore power system transmission nodes.

[0028] In this embodiment, the historical power transmission data of the port shore power system is obtained through the data acquisition server.

[0029] In this embodiment, performing fault prediction on the error-sensing node based on the historical power transmission data to obtain an abnormal node sequence specifically includes:

[0030] Performing time series forecasting on the historical power transmission data to obtain an operation curve of the transmission node;

[0031] determining a fault monitoring value according to the operating curve;

[0032] An abnormal node sequence is determined based on the fault monitoring value and the operating value of the error sensing node.

[0033] In this embodiment, the abnormality monitoring of the port shore power system is performed based on the abnormal load factor, and the monitoring results of the abnormal transmission nodes are obtained specifically including:

[0034] Obtaining operating parameters of the port shore power system, and then determining an abnormal risk value of the transmission node based on the operating parameters and the abnormal load factor;

[0035] The abnormal risk values ​​are cumulatively judged to obtain monitoring results of abnormal transmission nodes.

[0036] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0037] By collecting the mutual inductance data set of the port shore power system during power transmission, the power generation parameters are extracted from the mutual inductance data set; the mutual inductance data set is tested for anomalies to obtain the mutual inductance error, and the error sensing node is determined based on the mutual inductance error and the power generation parameters; the abnormal probability of the shore power system during power transmission is determined through the topological structure of the port shore power system transmission node and the error sensing node, and then the splitting point anomaly analysis is performed on the abnormal probability to obtain the abnormal isolation path; the historical power transmission data of the port shore power system is obtained, and the fault prediction of the error sensing node is performed on the historical power transmission data to obtain the abnormal node sequence, and then the abnormal load factor is determined through the abnormal node sequence and the abnormal isolation path; the port shore power system is monitored for abnormalities based on the abnormal load factor to obtain the monitoring result of the abnormal transmission node.

[0038] It can be seen that in this application, real-time fault monitoring and isolation of the port shore power system can be achieved; first, by collecting the mutual inductance data set of the port shore power system during power transmission and extracting key power generation parameters from it, the operating status of each transmission node of the system can be fully, continuously and in real time, avoiding information delay or omission, and providing a high-quality data basis for subsequent abnormal judgment; secondly, by performing an abnormality test on the mutual inductance data set, the mutual inductance error is obtained, and the error sensing node is jointly judged based on the error and the power generation parameters, avoiding the misjudgment problem caused by the single threshold judgment in the traditional method, and effectively improving the sensitivity and accuracy of fault diagnosis; then, the transmission node of the port shore power system is constructed For the topological network, the error-sensing nodes are combined to analyze the abnormal probability of power transmission in the shore power system, and further split point anomaly analysis is carried out. Finally, an abnormal isolation path is constructed, which achieves accurate fault location and effective isolation of the affected area, and improves the response efficiency of the shore power system to sudden anomalies. Then, combined with the historical power transmission data of the port shore power system, a fault prediction model is constructed to identify the potential abnormal trends of error-sensing nodes in advance, thereby enhancing the active defense capability of the system. Finally, the abnormal load factor is calculated by combining the abnormal node sequence and the abnormal isolation path, and the final monitoring judgment is made based on this factor, forming an abnormal detection closed-loop mechanism, which can improve the credibility of the monitoring results.

[0039] In summary, the technical solution adopted in this application can realize real-time fault monitoring and isolation of the port shore power system, so as to improve the credibility of the shore power system monitoring results. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 This is a flow chart of a remote real-time monitoring method for a port shore power system provided in accordance with the present application;

[0042] Figure 2 is an exemplary flow chart for determining mutual inductance error according to the present application;

[0043] Figure 3 This is an exemplary flow chart for determining the abnormal probability of shore power system power transmission according to the present application. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0045] An embodiment of the present application provides a remote real-time monitoring method for a port shore power system, the core of which is to collect visual parameters of the steel structure surface during the cutting process; normalize the parameter measurement values ​​during the steel cutting process based on the visual parameters, and then linearly map the normalized parameter measurement values ​​to a closed interval, and determine abnormal parameters through the closed interval and a preset specification threshold; construct a machine learning model for cutting process parameter regulation, and use the abnormal parameters to self-adjust the training parameters of the machine learning model based on cross-validation to obtain a hyperparameter feature topology, and then determine a dynamic compensation coefficient based on the hyperparameter feature topology; obtain the operating parameters of the cutting equipment, and adaptively and dynamically adjust the operating parameters based on the control rules of the logic constructed by the programmable logic controller through the dynamic compensation coefficient to obtain adaptive cutting parameters; determine the intelligent control result of the steel cutting process through the adaptive cutting parameters and the preset cutting target value.

[0046] In order to better understand the above technical solution, the following will be described in detail with reference to the accompanying drawings and specific implementation methods. Figure 1 As shown in FIG. 1 , this figure is an exemplary flow chart of a remote real-time monitoring method for a port shore power system according to this embodiment of the present application. The real-time monitoring method includes the following steps:

[0047] In step S1 , a mutual inductance data set of a port shore power system during power transmission is collected, and power generation parameters are extracted from the mutual inductance data set.

[0048] In specific implementation, the mutual inductance data set of the port shore power system is collected through a preset sensor array. That is, the mutual inductance sensors deployed at the port shore power transmission nodes convert the electromagnetic signals during the transmission process into digital signals, and the collected analog signals are converted into digital data using a high-sampling-rate analog-to-digital converter. The data is then transmitted to the monitoring center via industrial Ethernet to obtain the mutual inductance data set.

[0049] It should be noted that the mutual inductance data set in this application refers to a set of mutual inductance data of the port shore power transmission node, wherein the mutual inductance data refers to the electromagnetic signal data collected by the mutual inductance sensor, which can reflect information such as current, voltage and phase. The transmission nodes include: substations, busbars, and load terminals; in addition, the sampling rate in the high-sampling-rate analog-to-digital converter indicates the number of times the sensor collects data per second. In this embodiment, the sampling rate can be set between 1-10kHz, which is not limited here.

[0050] In specific implementation, the power generation parameters can be extracted from the mutual inductance data set through a data extraction model, wherein the data extraction model may include existing data extraction models such as Ohm's law, power calculation formula and phase angle analysis model; it should be noted that the power generation parameters are physical quantities that can be used to characterize the working state of the power generation system, and the power generation parameters include: generated power, active power, reactive power, power factor, frequency deviation, voltage offset, current distortion rate, etc.

[0051] In step S2, an abnormality check is performed on the mutual induction data set to obtain a mutual induction error, and an error sensing node is determined based on the mutual induction error and the power generation parameter.

[0052] Preferably, in this embodiment, reference Figure 2 As shown in FIG, this figure is an exemplary flow chart of determining the mutual inductance error in an embodiment of the present application. In this embodiment, an abnormality check is performed on the mutual inductance data set to obtain the mutual inductance error, which can be specifically achieved by the following steps:

[0053] First, in step S21, the mutual induction data in the mutual induction data set is subjected to denoising, normalization, and synchronization correction processing to obtain processed mutual induction data;

[0054] Then, in step S22, the processed mutual inductance data is subjected to time series anomaly detection analysis to obtain a mutual inductance error.

[0055] In a specific implementation, first, wavelet threshold denoising is used to eliminate random interference in the sampling process. That is, a three-layer wavelet denoising process is performed on the mutual inductance data in the mutual inductance data set using the db4 wavelet basis, which can retain the main components of the signal. In other embodiments, wavelet basis of other sizes or other denoising algorithms can also be used for denoising, which is not limited here. Maximum and minimum normalization is used to uniformly scale the data features of different channels. Then, data of different measurement points are aligned based on timestamps to obtain processed mutual inductance data. The mutual inductance data has the characteristics of noise suppression, scale unification, and time series consistency. Then, time series modeling analysis is performed on the processed mutual inductance data, and the median absolute deviation is used to determine anomalies in the residual sequence. That is, if the residual of a data transmission node at a certain moment exceeds a set threshold (such as three times the median absolute deviation), it is determined to be an abnormal transmission node. The deviation amplitude of the abnormal point is output through the median absolute deviation algorithm, and the deviation amplitude of the abnormal transmission node is then used as the mutual inductance error.

[0056] It should be noted that the mutual inductance error in this application refers to the outlier deviation of the mutual inductance data compared to the expected value, and the processed mutual inductance data refers to the standardized mutual inductance data that has completed noise reduction, normalization and multi-channel synchronous correction, which is used for subsequent abnormality analysis; in addition, in this embodiment, through timing anomaly analysis and dynamic error modeling, high-sensitivity identification of hidden anomalies and gradual errors can be achieved, and it can be expanded to adapt to the data formats of multiple types of mutual inductance elements (such as current, voltage, and combined mutual inductors), and is suitable for heterogeneous acquisition platforms, for subsequent modules to perform error sensing node identification and abnormal path derivation.

[0057] In this embodiment, the error sensing node may be determined based on the mutual inductance error and the power generation parameter in the following manner:

[0058] Mapping the mutual inductance error and the power generation parameter to the same scale through normalization processing to obtain normalized mutual inductance error and power generation parameter;

[0059] The abnormal sensitivity of the transmission node of the port shore power system is determined based on the normalized mutual inductance error and power generation parameters;

[0060] The abnormality detection nodes of the port shore power system are screened according to the abnormality sensitivity to obtain error sensing nodes.

[0061] In the specific implementation, first, the collected mutual inductance error and the extracted power generation parameters are normalized respectively, and each data is mapped to a unified scale (such as the 0-1 interval) to eliminate the influence of different dimensions and numerical ranges on subsequent calculations. For example, the maximum and minimum normalization method is used to process the mutual inductance error and power generation parameters so that both are in the 0-1 range, and the normalized mutual inductance error and power generation parameters are obtained. In other embodiments, other normalization techniques can also be used to map to other specified intervals, which are not limited here; then, for each port shore power system transmission node, according to The normalized mutual inductance error and power generation parameter allocation weights are used, and the abnormal sensitivity of each transmission node is calculated using the weighted integration method based on the normalized data. A threshold of 0.7 is set as the abnormal screening criterion. Finally, the abnormal transmission nodes are reviewed using the local statistical clustering method, that is, the K-means clustering technology is used to monitor the fluctuation of the abnormal sensitivity of the transmission nodes, and then the transmission nodes with abnormal sensitivity fluctuations greater than the set threshold of 0.7 are regarded as error-sensing nodes. Among them, the abnormal screening criterion can also set the threshold between 0.6 and 0.9 based on historical experience, which is not limited here.

[0062] It should be noted that the abnormal sensitivity in this application refers to a quantitative evaluation index of the abnormal risk of each transmission node after comprehensively considering the normalized mutual inductance error and power generation parameters. The error sensing node is a key transmission node with a higher abnormal risk determined after screening the abnormal sensitivity of the transmission node; in addition, in this embodiment, multi-dimensional data fusion is achieved through data normalization and multi-indicator weighted calculation, which improves the accuracy of abnormal sensitivity judgment, further reduces the misjudgment rate through the secondary verification mechanism, and improves the accuracy of the system's response to abnormal conditions.

[0063] In step S3, the abnormal probability of shore power system power transmission is determined by the topological structure of the port shore power system transmission node and the error sensing node, and then the abnormal probability is subjected to splitting point abnormality analysis to obtain an abnormal isolation path.

[0064] Preferably, in this embodiment, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart for determining the abnormal probability of shore power system power transmission in an embodiment of the present application. In this embodiment, the abnormal probability of shore power system power transmission is determined based on the topological structure of the port shore power system transmission node and the error sensing node, which can be specifically implemented by the following steps:

[0065] First, in step S31, the topological structure of the port shore power system transmission nodes is converted into a directed weighted graph;

[0066] Then, in step S32, error propagation derivation is performed on the directed weighted graph according to the error sensing node to obtain abnormal transmission probabilities of different transmission nodes in the directed weighted graph;

[0067] Finally, in step S33 , the abnormality probability of the shore power system during power transmission is determined by using all abnormality transmission probabilities.

[0068] In a specific implementation, a transmission node mapping algorithm is used to convert each transmission node in the port shore power system into a directed weighted graph based on the actual power transmission path. The edge weights of the directed weighted graph can be comprehensively assigned based on the transmission impedance and data transmission delay. That is, the average value of the transmission impedance and data transmission delay is used as the edge weight of the directed weighted graph. The transmission impedance and data transmission delay can be determined by testing the network communication of the shore power system. Then, the error-sensing node is used as the initial activation point, and an error influence is applied to its adjacent transmission nodes in the graph. That is, the error propagation factors with different edge weights are determined through the edge weight allocation in the prior art. Each error propagation factor is then used as the calculation weight of a recursive algorithm. The recursive algorithm with the set calculation weights is used to calculate the abnormal transmission probability of different transmission nodes in the directed weighted graph. Finally, the abnormal transmission probability of each transmission node is comprehensively calculated. By normalizing all abnormal transmission probabilities and taking a weighted sum of all normalized abnormal probabilities, the abnormal probability of power transmission in the shore power system is obtained. The weight of the weighted sum is determined by the ratio of the error propagation factors.

[0069] It should be noted that the abnormal probability of shore power system power transmission in this application refers to the normalized risk index of quantified abnormality of each transmission node after integrating all abnormal transmission probabilities. The directed weighted graph represents the port shore power system transmission node as the vertex, the connection relationship between the transmission nodes as the edge, and each edge is assigned a weight reflecting the power transmission characteristics (such as impedance, load, etc.). The abnormal transmission probability represents the probability value of the abnormal impact transmitted from the error sensing node to other transmission nodes in the directed weighted graph; in addition, the port shore power system transmission nodes are globally expressed through the graph model. Compared with single-point monitoring, the spatial propagation analysis of the abnormal impact can be realized. The error propagation prediction can quantify the impact of the error sensing node on other transmission nodes in the entire network, which is conducive to identifying the risk of fault propagation.

[0070] In this embodiment, the abnormal probability is subjected to splitting point abnormality analysis to obtain the abnormal isolation path in the following manner, namely:

[0071] dividing abnormal splitting points according to the abnormal probability of power transmission of the shore power system;

[0072] Performing isolation processing on the abnormal splitting points to obtain an abnormal transmission node subgraph of the topological structure of the port shore power system transmission nodes;

[0073] The abnormal isolation path is determined through the abnormal transmission node subgraph of the topological structure of the port shore power system transmission nodes.

[0074] In the specific implementation, first, a clustering or threshold segmentation method is used to take the transmission node area with a higher abnormal probability during shore power system power transmission as the abnormal splitting point. For example, according to the set abnormal probability threshold of shore power system power transmission (such as 0.8), the transmission nodes with abnormal probability exceeding the abnormal probability threshold during shore power system power transmission in the topology map are clustered and analyzed, and then the image area composed of the nodes exceeding the abnormal probability threshold obtained by clustering is taken as the abnormal splitting point area; then, the abnormal splitting points in the abnormal splitting point area are partitioned, that is, the abnormal splitting point area is segmented at the abnormal splitting point using the minimum segmentation algorithm, and then the segmented image area is taken as the shore power system transmission area. The abnormal transmission node subgraph of the node topological structure is constructed; finally, within the abnormal transmission node subgraph, the Dijkstra algorithm is applied to calculate the shortest path from the abnormal source to the isolation boundary according to the edge weights and abnormal transmission probabilities between each transmission node, and the shortest path is then used as the abnormal isolation path, wherein the abnormal splitting point refers to the key transmission node area determined by setting a threshold or clustering analysis in the abnormal probability distribution during power transmission of the global shore power system. This area plays a bridging role in the propagation of abnormalities. The abnormal transmission node subgraph is a local subgraph divided from the original port shore power system transmission node topology graph after isolating the abnormal splitting point. The transmission nodes in this subgraph all have a high abnormal risk.

[0075] It should be noted that the abnormal isolation path in this application represents the optimal path planned in the abnormal transmission node subgraph based on the transmission weight and abnormal transmission probability between the transmission nodes, which is used to isolate the channel for abnormal diffusion; in addition, the use of splitting point division can effectively identify and isolate the abnormal diffusion area from a global topological perspective. The isolation path constructed based on the abnormal transmission node subgraph can isolate abnormal conduction in the shortest time and reduce the risk of abnormal diffusion.

[0076] In step S4, historical power transmission data of the port shore power system is obtained, and fault prediction is performed on the error sensing node based on the historical power transmission data to obtain an abnormal node sequence, and then an abnormal load factor is determined through the abnormal node sequence and the abnormal isolation path.

[0077] In specific implementation, the historical power transmission data of the port shore power system is obtained through a data acquisition server, wherein the data acquisition server is a power data acquisition server equipped with a SCADA platform, which can extract historical power transmission data from the database of the SCADA platform. The historical power transmission data includes historical power parameters such as voltage, current, power, active power and reactive power. After preprocessing the collected data using a Python script, the data is converted into a standardized format and written in batches into a time series database.

[0078] In this embodiment, fault prediction is performed on the error-sensing node based on the historical power transmission data to obtain an abnormal node sequence, which can be specifically performed in the following manner, namely:

[0079] Performing time series forecasting on the historical power transmission data to obtain an operation curve of the transmission node;

[0080] determining a fault monitoring value according to the operating curve;

[0081] An abnormal node sequence is determined based on the fault monitoring value and the operating value of the error sensing node.

[0082] In a specific implementation, the collected historical power transmission data is preprocessed (including missing value filling, noise filtering, and timestamp alignment), and a time series prediction model is used to perform trend prediction on the operating data of each transmission node, thereby obtaining an operating curve for each transmission node. For example, the historical power transmission data can be trained and predicted using an LSTM model to generate a transmission node operating curve. Then, a residual analysis method is used to quantify the deviation between the predicted curve and the actual curve. When the deviation exceeds a preset threshold, a fault monitoring value for the transmission node is determined. The fault monitoring value can be obtained by calculating key indicators such as the residual, deviation, and fluctuation amplitude between the actual operating value and the predicted value, and serves as an important basis for determining whether a transmission node has a fault trend. The preset threshold can be obtained by performing a regression analysis on the historical power transmission data using an autoregressive analysis algorithm in the prior art. Finally, the extracted fault monitoring value is compared with the operating value of the error-sensing node. The transmission node with an operating value greater than the fault monitoring value is identified as an abnormal transmission node, and the collection of all abnormal transmission nodes is then identified as an abnormal node sequence. The operating value refers to the value of the power parameter of the shore power system transmission node during operation.

[0083] It should be noted that the fault monitoring value in this application represents the residual or deviation extracted after comparing the operating curve with the actual operating data, which is used to reflect the quantitative indicator of the potential fault risk of the transportation node; the abnormal node sequence is a set of error-sensing nodes that are determined to have potential fault trends after being screened by the fault monitoring value; in addition, the trend curve of the future operating status of each transportation node obtained by the time series prediction model can capture the operating trend of the transportation node, effectively improving the sensitivity and accuracy of anomaly detection.

[0084] In this embodiment, the abnormal load factor may be determined by using the abnormal node sequence and the abnormal isolation path in the following manner:

[0085] Determining a risk score for each abnormal transmission node in the abnormal node sequence;

[0086] The contribution of the abnormal isolation path is screened according to all risk scores to obtain the risk contribution of different transmission nodes;

[0087] An abnormal load factor is determined based on all risk scores and all risk contributions.

[0088] In specific implementation, first, the residual, deviation and abnormal duration of each abnormal transmission node are normalized and assigned corresponding weights to obtain a transmission node risk score matrix, and then the risk score of each abnormal matrix is ​​extracted from the risk score matrix; then, the transmission nodes in the abnormal isolation path are arranged in path order, the risk transfer and cumulative effect between the transmission nodes are analyzed, and the risk scores of each transmission node on the path are integrated using a weighted integral or cumulative model to obtain the overall risk contribution of the path. For example, a weighted accumulation algorithm is applied to the abnormal isolation path to sum the risk values ​​from the starting transmission node to the isolation boundary of the path. Through this step, the risk contribution of different transmission nodes can be obtained; finally, the risk contribution and risk score are weightedly fused, and combined with the global normalization method, the abnormal load factor of each transmission node or area is finally determined. For example, the abnormal load factor is the weighted average of the risk score of each transmission node and the risk contribution of the isolation path, and the results of all transmission nodes are normalized to ensure that the load factor value is between 0 and 1.

[0089] It should be noted that the abnormal load factor in this application is a quantitative indicator that comprehensively reflects the cumulative effect of local abnormal risk and the isolation effect of abnormal propagation. It is usually expressed as a value between 0 and 1. The larger the value, the higher the abnormal load. The risk score of the abnormal transmission node is a risk indicator calculated based on the fault monitoring value, abnormal duration and abnormal transmission probability of each transmission node. By integrating the abnormal node sequence and isolation path information, it not only takes into account the risk status of a single transmission node, but also reflects the diffusion effect of the abnormality in the network. It has a more global perspective than the traditional evaluation method that relies only on single-point indicators.

[0090] In step S5, the port shore power system is monitored for abnormalities based on the abnormal load factor to obtain monitoring results of abnormal transmission nodes.

[0091] In this embodiment, the abnormality monitoring of the port shore power system is performed based on the abnormal load factor, and the monitoring result of the abnormal transmission node is obtained in the following manner, namely:

[0092] Obtaining operating parameters of the port shore power system, and then determining an abnormal risk value of the transmission node based on the operating parameters and the abnormal load factor;

[0093] The abnormal risk values ​​are cumulatively judged to obtain monitoring results of abnormal transmission nodes.

[0094] In the specific implementation, first, the operating parameters of each transmission node are read in real time through the SCADA platform interface. The operating parameters refer to the electrical parameters collected in real time during the operation of each transmission node of the port shore power system, including voltage, current, power, frequency and load status. The maximum and minimum normalization method is used to ensure that the data are in a unified dimension to facilitate subsequent calculations; then, the abnormal risk value is determined by calculating the parameter deviation of the abnormal load factor and the operating parameters. Among them, the inverse of the Pearson correlation coefficient of the operating parameter can be used as the parameter deviation of the operating parameter. The abnormal risk value can be obtained by the following formula: That is: abnormal risk value = α × parameter deviation + β × abnormal load factor, where α and β are weight parameters, which can be preset based on historical experience. After normalizing the calculation results, the abnormal risk value of each transportation node can be obtained; finally, the abnormal risk value of each transportation node within the continuous monitoring period is accumulated and judged through time series integration technology, and the persistence and cumulative effect of the risk value are evaluated through sliding window or time series integration. When the cumulative risk exceeds the preset threshold, the transportation node is determined to be an abnormal transportation node, and its abnormal monitoring results (including risk level and abnormal duration information) are output.

[0095] It should be noted that the abnormal risk value in this application is a risk quantification indicator calculated based on operating parameters and abnormal load factors, which is used to judge the abnormal state of the transportation node. The higher the value, the greater the abnormal risk; the abnormal transportation node monitoring results include the judgment of the abnormal state of each transportation node and the operating parameters judged as risks.

[0096] It can be seen that in this application, real-time fault monitoring and isolation of the port shore power system can be achieved; first, by collecting the mutual inductance data set of the port shore power system during power transmission and extracting key power generation parameters from it, the operating status of each transmission node of the system can be fully, continuously and in real time, avoiding information delay or omission, and providing a high-quality data basis for subsequent abnormal judgment; secondly, by performing an abnormality test on the mutual inductance data set, the mutual inductance error is obtained, and the error sensing node is jointly judged based on the error and the power generation parameters, avoiding the misjudgment problem caused by the single threshold judgment in the traditional method, and effectively improving the sensitivity and accuracy of fault diagnosis; then, the transmission node of the port shore power system is constructed For the topological network, the error-sensing nodes are combined to analyze the abnormal probability of power transmission in the shore power system, and further split point anomaly analysis is carried out. Finally, an abnormal isolation path is constructed, which achieves accurate fault location and effective isolation of the affected area, and improves the response efficiency of the shore power system to sudden anomalies. Then, combined with the historical power transmission data of the port shore power system, a fault prediction model is constructed to identify the potential abnormal trends of error-sensing nodes in advance, thereby enhancing the active defense capability of the system. Finally, the abnormal load factor is calculated by combining the abnormal node sequence and the abnormal isolation path, and the final monitoring judgment is made based on this factor, forming an abnormal detection closed-loop mechanism, which can improve the credibility of the monitoring results.

[0097] In summary, the technical solution adopted in this application can realize real-time fault monitoring and isolation of the port shore power system, so as to improve the credibility of the shore power system monitoring results.

[0098] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, magnetic disk storage, or magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0100] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

Claims

1. A remote real-time monitoring method for a port shore power system, characterized in that: The real-time monitoring method comprises the following steps: collecting a mutual induction data set during power transmission of the port shore power system, and extracting power generation parameters from the mutual induction data set; performing an anomaly test on the mutual induction data set to obtain a mutual induction error, and determining an error sensing node based on the mutual induction error and the power generation parameter; Determining the abnormal probability of shore power system power transmission through the topological structure of the port shore power system transmission node and the error sensing node, and then performing splitting point abnormality analysis on the abnormal probability to obtain an abnormal isolation path; Acquire historical power transmission data of the port shore power system, perform fault prediction on the error sensing node based on the historical power transmission data, obtain an abnormal node sequence, and then determine an abnormal load factor based on the abnormal node sequence and the abnormal isolation path; Performing abnormal monitoring on the port shore power system based on the abnormal load factor to obtain monitoring results of abnormal transmission nodes; The mutual induction error is obtained by performing an anomaly check on the mutual induction data set. Specifically, the mutual induction error is obtained by: performing denoising, normalization, and synchronization correction processing on the mutual induction data in the mutual induction data set to obtain processed mutual induction data; Perform time series anomaly detection and analysis on the processed mutual inductance data to obtain the mutual inductance error; The mutual inductance error refers to the outlier deviation of the mutual inductance data from the expected value.

2. A remote real-time monitoring method for a port shore power system according to claim 1, characterized in that: The mutual induction data set of the port shore power system is collected through a preset sensor array.

3. A remote real-time monitoring method for a port shore power system according to claim 1, characterized in that: The power generation parameters are extracted from the mutual induction data set by a data extraction model.

4. A remote real-time monitoring method for a port shore power system according to claim 1, characterized in that: Determining the error sensing node based on the mutual inductance error and the power generation parameter specifically includes: Mapping the mutual inductance error and the power generation parameter to the same scale through normalization processing to obtain normalized mutual inductance error and power generation parameter; The abnormal sensitivity of the transmission node of the port shore power system is determined based on the normalized mutual inductance error and power generation parameters; The abnormality detection nodes of the port shore power system are screened according to the abnormality sensitivity to obtain error sensing nodes.

5. The remote real-time monitoring method for a port shore power system according to claim 1, characterized in that: Determining the abnormal probability of shore power system power transmission through the topological structure of the port shore power system transmission node and the error sensing node specifically includes: Convert the topological structure of the port shore power system transmission nodes into a directed weighted graph; Performing error propagation deduction on the directed weighted graph according to the error sensing node to obtain abnormal transmission probabilities of different transmission nodes in the directed weighted graph; The abnormal probability of shore power system power transmission is determined by all abnormal transmission probabilities.

6. A remote real-time monitoring method for a port shore power system according to claim 1, characterized in that: Performing split point anomaly analysis on the anomaly probability to obtain an anomaly isolation path specifically includes: dividing abnormal splitting points according to the abnormal probability of power transmission of the shore power system; Performing isolation processing on the abnormal splitting points to obtain an abnormal transmission node subgraph of the topological structure of the port shore power system transmission nodes; The abnormal isolation path is determined through the abnormal transmission node subgraph of the topological structure of the port shore power system transmission nodes.

7. The remote real-time monitoring method for a port shore power system according to claim 1, characterized in that: The historical power transmission data of the port shore power system is obtained through the data acquisition server.

8. The remote real-time monitoring method for a port shore power system according to claim 1, characterized in that: Performing fault prediction on the error-sensing node based on the historical power transmission data to obtain an abnormal node sequence specifically includes: Performing time series forecasting on the historical power transmission data to obtain an operation curve of the transmission node; determining a fault monitoring value according to the operating curve; An abnormal node sequence is determined based on the fault monitoring value and the operating value of the error sensing node.

9. The remote real-time monitoring method for a port shore power system according to claim 1, characterized in that: Based on the abnormal load factor, the abnormality monitoring of the port shore power system is performed, and the monitoring results of the abnormal transmission nodes are obtained, which specifically include: Obtaining operating parameters of the port shore power system, and then determining an abnormal risk value of the transmission node based on the operating parameters and the abnormal load factor; The abnormal risk values ​​are cumulatively judged to obtain monitoring results of abnormal transmission nodes.

Images